Ifp Energies Nouvelles

Youri Hamon

Didier Granjeon

Vincent Clochard

Benoit Chauveau

Maxime Moreaud

Antoine Bouziat

Mathieu Feraille

Mickael Barbier

Sylvain Desroziers

The present invention relates to a method of detecting a geological constituent (cge) of a rock sample, by use of a machine learning method (ALG) trained with a limited number of training images (IAP), through segmentation (SEG) and partitioning (DEC) of training images (IAP) into multiple patches.

Method of detecting at least one geological constituent of a rock sample

The invention is a method of exploiting hydrocarbons within a sedimentary basin, by stratigraphic simulation coupled with a hydrologic model and a diagenetic model. A gridded representation of the basin, comprising at least a mineralogical composition and a porosity within each cell, is determined by means of a stratigraphic simulator for at least one time step. Then, at least one hydrologic zone is delimited using a hydrologic model, and at least one chemical composition of the fluids and a direction of circulation of the fluids are determined in each cell located in the zone. At least the chemical composition of the fluids, the mineralogical composition and the porosity are then updated in each cell of the gridded representation with a diagenetic model comprising a hydrologic flux balance, established using at least the directions of circulation of the fluids and from which a cell visiting order is determined for the fluids.

Method of exploiting a sedimentary basin comprising hydrocarbons, using stratigraphic modelling

Growing community of inventors

Chatou, France

Youri Hamon